Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.4733. Min Act: -0.1700
Data Index: 8293967 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.3483. Min Act: -0.1700
Data Index: 4169047 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.3483. Min Act: -0.1700
Data Index: 2129097 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.3170. Min Act: -0.1700
Data Index: 2833500 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.2858. Min Act: -0.1700
Data Index: 5625249 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.2858. Min Act: -0.1700
Data Index: 5866287 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.2545. Min Act: -0.1700
Data Index: 6008098 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.2233. Min Act: -0.1700
Data Index: 8706817 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.2233. Min Act: -0.1700
Data Index: 3397879 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.2233. Min Act: -0.1700
Data Index: 6716573 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.2545. Min Act: -0.1700
Data Index: 4237136 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.2545. Min Act: -0.1700
Data Index: 8323852 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.1920. Min Act: -0.1700
Data Index: 707565 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.1607. Min Act: -0.1700
Data Index: 1476868 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.1920. Min Act: -0.1700
Data Index: 7116578 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.1607. Min Act: -0.1700
Data Index: 2077057 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.1607. Min Act: -0.1700
Data Index: 4615720 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.1607. Min Act: -0.1700
Data Index: 7176898 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.1607. Min Act: -0.1700
Data Index: 1938785 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4733. Min Range: -4.4733
Max Act: 4.1295. Min Act: -0.1700
Data Index: 5384191 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19